Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    caveats and reinforcement learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    极
    0.64
    ذ
    0.63
    淞
    0.57
     extraordinary
    0.56
     Villeneuve
    0.55
    極
    0.52
    sv
    0.52
     params
    0.52
     hood
    0.52
    ถือ
    0.51
    POSITIVE LOGITS
     onOptions
    0.67
    ERTY
    0.64
     dull
    0.62
     நம்ம
    0.61
     블
    0.58
    Blogs
    0.58
    бі
    0.57
     biogas
    0.57
    aughan
    0.57
     SIT
    0.56
    Act Density 0.135%

    No Known Activations